EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data

Documenti analoghi

• Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning
  di: Liu, Shaohuai, et al.
  Pubblicazione: (2026)
• Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own
  di: Ye, Weirui, et al.
  Pubblicazione: (2023)
• Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos
  di: Ye, Weirui, et al.
  Pubblicazione: (2025)
• EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
  di: Evers, Thomas, et al.
  Pubblicazione: (2026)
• PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning
  di: Gao, Tian, et al.
  Pubblicazione: (2024)